CN115731003A - Product recommendation method and device - Google Patents
Product recommendation method and device Download PDFInfo
- Publication number
- CN115731003A CN115731003A CN202211508301.6A CN202211508301A CN115731003A CN 115731003 A CN115731003 A CN 115731003A CN 202211508301 A CN202211508301 A CN 202211508301A CN 115731003 A CN115731003 A CN 115731003A
- Authority
- CN
- China
- Prior art keywords
- product
- recommendation
- data
- determining
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a product recommendation method and device, which relate to big data, and the method comprises the following steps: determining a model recommended product list according to the product sales data and the historical purchase data of the customer; acquiring input manual recommendation data; determining parameters of a marketing rule model by adopting a parameter configuration mode; determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters; and determining the personalized recommended product according to the product recommendation strategy. According to the invention, different products can be recommended for the customer based on the big data algorithm and the recommendation strategy model, the purpose that the customer recommends thousands of people and thousands of faces and accurately markets is achieved, and the customer is stimulated to purchase various bank products.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a product recommendation method and device.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
With the wide application of big data analysis in the banking industry, the analysis of historical data such as the sales volume of products and the purchase of products gradually plays an increasing role in the accurate marketing of the banking industry. In order to improve the exposure and marketing of bank bright-spot products, the product recommendation system analyzes the past product interaction behaviors of customers and the historical sales conditions of products by using model learning to quickly generate a personalized product recommendation list. In the banking field, the diversity of customers may result in a portion of customers having poor big data information.
The existing bank product recommendation is a simple model recommendation product, risk control and compliance control are not in place, meanwhile, flexibility of product allocation is poor, product recommendation results cannot be manually intervened, and inquiry and explanation cannot be well carried out on customer questions.
Therefore, how to provide a new solution, which can solve the above technical problems, is a technical problem to be solved in the art.
Disclosure of Invention
The embodiment of the invention provides a product recommendation method, which can recommend different products for a customer by a big data algorithm and a recommendation strategy model, achieves the aims of recommending thousands of people and accurate marketing by the customer, and stimulates the customer to purchase various bank products, and comprises the following steps:
determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
acquiring input manual recommendation data;
determining marketing rule model parameters in a parameter configuration mode;
determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters;
and determining the personalized recommended products according to the product recommendation strategy.
An embodiment of the present invention further provides a product recommendation device, including:
the model recommended product list determining module is used for determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
the manual recommendation data acquisition module is used for acquiring input manual recommendation data;
the marketing rule model parameter determining module is used for determining marketing rule model parameters in a parameter configuration mode;
the product recommendation strategy determination module is used for determining a product recommendation strategy according to the model recommendation product list, the artificial recommendation data and the marketing rule model parameters;
and the personalized recommended product determining module is used for determining a personalized recommended product according to the product recommending strategy.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the product recommendation method is implemented.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the above-mentioned product recommendation method.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the above product recommendation method.
The embodiment of the invention provides a product recommendation method and device, and the method comprises the following steps: determining a model recommended product list according to the product sales data and the historical purchase data of the customer; acquiring input manual recommendation data; determining marketing rule model parameters in a parameter configuration mode; determining a product recommendation strategy according to the model recommendation product list, the manual recommendation data and the marketing rule model parameters; and determining the personalized recommended product according to the product recommendation strategy. Different products can be recommended for the customer based on a big data algorithm and a recommendation strategy model, the purpose that the customer recommends thousands of people and thousands of faces and accurate marketing is achieved, the customer is stimulated to purchase various products of a bank, and the bank performance is improved. The system is complete, a recommendation rule setting interface is provided, and a recommendation model is automatically generated for real-time product recommendation. The method has good flexibility, and business personnel can flexibly set rules according to activity conditions through parameter control. The maintenance cost is low: related information can be set through parameters, only the parameters need to be adjusted if needed to be changed in the system maintenance process, and version development is generally not needed. The method has the characteristics of high response and high complexity rule support, and can bring better use experience to customers.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
fig. 1 is a schematic diagram of a product recommendation method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a process of determining a model recommended product list in a product recommendation method according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a process of determining marketing rule model parameters according to a product recommendation method in an embodiment of the present invention.
Fig. 4 is a flowchart of determining a product recommendation policy of a product recommendation method according to an embodiment of the present invention.
FIG. 5 is a schematic diagram of a computer apparatus for executing a product recommendation in accordance with the present invention.
Fig. 6 is a schematic diagram of a product recommendation device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
Fig. 1 is a schematic diagram of a product recommendation method according to an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a product recommendation method, which can recommend different products for a customer by using a big data algorithm and a recommendation policy model, and achieve the purpose of recommending thousands of people and thousands of faces for the customer and realizing accurate marketing, and stimulate the customer to purchase various products in a bank, and the method includes:
step 101: determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
step 102: acquiring input manual recommendation data;
step 103: determining marketing rule model parameters in a parameter configuration mode;
step 104: determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters;
step 105: and determining the personalized recommended products according to the product recommendation strategy.
The embodiment of the invention provides a product recommendation method, which comprises the following steps: determining a model recommended product list according to the product sales data and the historical purchase data of the customer; acquiring input manual recommendation data; determining marketing rule model parameters in a parameter configuration mode; determining a product recommendation strategy according to the model recommendation product list, the manual recommendation data and the marketing rule model parameters; and determining the personalized recommended product according to the product recommendation strategy. Different products can be recommended for the client based on a big data algorithm and a recommendation strategy model, the purpose that the client recommends thousands of people and sales is achieved accurately, the client is stimulated to purchase various products of a bank, and the bank performance is improved. The system is relatively perfect, a recommendation rule setting interface is provided, and a recommendation model is automatically generated for real-time product recommendation. The method has good flexibility, and business personnel can flexibly set rules according to activity conditions through parameter control. The maintenance cost is low: related information can be set through parameters, only the parameters need to be adjusted if needed to be changed in the system maintenance process, and version development is generally not needed. The method has the characteristics of high response and high complexity rule support, and can bring better use experience to customers.
Most of the existing modes adopted by the product recommendation of the customer manager of the bank are product recommendation through pure machine learning, the basis of the machine learning is recommendation according to the product sales condition and customer interaction, but due to the problems of compliance and risk, not all products can be recommended to customers, and the simple model recommendation cannot well achieve the short-term sales target of the customer manager. The special product of the I line cannot be well recommended for the situations of clients who do not perform risk assessment in the I line, newly-opened clients who do not perform risk assessment in the I line, clients who do not perform risk assessment in the I line and the like.
The invention provides a real-time product recommendation method based on a strategy model, which comprises the four aspects of model recommendation, accurate recommendation of a customer manager and a chief, marketing rule model setting and risk real-time shielding, and realizes accurate marketing of thousands of people for customer marketing by adding configured manual recommendation and risk and compliance control on the basis of model recommendation of big data.
The invention provides a real-time product recommendation method based on a strategy model, which comprises the four aspects of model recommendation, accurate recommendation of a customer manager and a head office, marketing rule model setting and risk real-time shielding. The product recommendation method has the characteristics of accurate marketing of a set customer group, recommendation risk avoidance, timely intervention of manual recommendation, thousands of people and thousands of faces of a recommendation scheme and the like.
The model recommendation can be used for analyzing and modeling according to big data such as product historical sales, customer-product interaction, customer groups and the like, and recommending a part of products aiming at different types of products. And the client manager and the accurate recommendation of the head office can make up the blank condition of model recommendation, and supplement a product recommendation list according to short-term hot-pushing products in the head office or the region. And the marketing strategy model controls risk compliance of the recommended products according to conditions such as compliance, qualification and risk, and controls risk shielding of the recommended product list in real time according to risk evaluation of the customer at the bank, so that the risk of the recommended product list is controllable and compliant.
When the product recommendation method provided by the embodiment of the present invention is implemented specifically, in an embodiment, the method includes:
determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
acquiring input manual recommendation data;
determining parameters of a marketing rule model by adopting a parameter configuration mode;
determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters;
and determining the personalized recommended products according to the product recommendation strategy.
The invention provides a real-time product recommendation method based on a strategy model, which generates model recommendation products based on Mapreduce big data analysis and realizes free configuration updating of marketing rules and configuration of accurate recommendation of a customer manager and a head office by matching with friendly interface interaction.
Fig. 2 is a schematic diagram of a process of determining a model recommended product list of a product recommendation method according to an embodiment of the present invention, and as shown in fig. 2, when a product recommendation method according to an embodiment of the present invention is implemented in detail, in an embodiment, determining a model recommended product list according to product sales data and customer historical purchase data includes:
step 201: acquiring product sales data and customer historical purchase data from a trading system in real time through Kafka;
step 202: and classifying the product sales data by using MapReduce, sequencing each product type according to the product sales, performing weight adjustment on the products by combining with the historical purchase data of customers, and determining a model recommended product list.
In a specific implementation of the product recommendation method provided by the embodiment of the present invention, in an embodiment, the manual recommendation data includes: recommending data by lines, recommending data of maintaining customer products by a customer manager and recommending data of recommending key products by a head office.
Fig. 3 is a schematic diagram of a process of determining marketing rule model parameters of a product recommendation method according to an embodiment of the present invention, and as shown in fig. 3, when a product recommendation method according to an embodiment of the present invention is implemented specifically, in an embodiment, a parameter configuration manner is adopted to determine marketing rule model parameters, including:
step 301: determining parameter configuration data in response to selection of a parameter configuration item by a customer manager; the parameter configuration item comprises: setting the working qualification, setting the third-level sales qualification of a client manager, and comparing the product recommendation requirement based on the risk level of the client, the requirement of qualified investors, a model and the accurate recommendation quantity;
step 302: and determining parameters of the marketing rule model according to the parameter configuration data.
Fig. 4 is a flowchart of determining a product recommendation policy of a product recommendation method according to an embodiment of the present invention, and as shown in fig. 4, when the product recommendation method provided in the embodiment of the present invention is implemented specifically, in an embodiment, determining a product recommendation policy according to a model recommendation product list, manual recommendation data, and marketing rule model parameters includes:
acquiring a mobile phone number and a customer manager number from the marketing rule model parameters;
judging whether the client is the client in the local bank or not according to the mobile phone number and the client manager number, if so, judging whether the client manager exists or not, and if so, acquiring the client risk level and the manager qualification from the marketing rule model parameters;
judging whether the sales qualification of the customer manager exists or not according to the risk level of the customer and the qualification of the manager, and reading a model recommended product list and manual recommended data if the sales qualification of the customer manager exists; when the manual recommendation data is empty, selecting the customer manager number to obtain the corresponding uploading and sending management qualification; determining that the manual recommendation content is written in the manual recommendation data according to the uplink physical qualification and the client risk level;
and determining a product recommendation strategy according to the model recommendation product list and the manual recommendation data, the manager qualification and the client risk level and the quantity rule.
When the product recommendation method provided by the embodiment of the present invention is implemented specifically, in an embodiment, determining a personalized recommended product according to a product recommendation policy includes:
and selecting and assembling the recommended products according to the product recommendation strategy, and determining the personalized recommended products.
The following briefly describes a product recommendation method provided by an embodiment of the present invention with reference to specific scenarios:
s1: the model recommends that the products are classified by acquiring data according to sales of various products and historical product purchases of the products by the customers in real time, for example, by acquiring the data from a trading system in real time through Kafka, and using a big data analysis and calculation tool MapReduce. And (4) recommending high-sales products according to the product sales volume for each product type, and adjusting the weight by combining with the high-frequency purchase records of specific customers, thereby finally calculating a model recommended product list of each customer.
And S2, accurately recommending by a client manager and a branch/head office, adding a product recommendation manual intervention module in the scheme, providing recommendation modes such as branch recommendation, client manager recommendation for maintaining client products, head office key product recommendation and the like on an online interface, playing the effects of improving exposure frequency and accurately recommending products for key products, simultaneously being compatible with a bottom-pocketing scheme with empty model data, and being capable of providing selected product recommendation data under various conditions such as newly-opened clients, non-my clients, non-maintaining clients and the like.
And S3, setting parameters of the marketing rule model, wherein the marketing rule model designed by the scheme adopts a parameter configuration mode, so that a service manager can flexibly configure the compliance control of each product conveniently. Providing an interface for carrying out compliance setting, wherein selectable items such as customer manager fund employment qualification setting, customer manager three-level sales qualification setting, product recommendation requirement based on customer risk level, qualified investor requirement, model and accurate recommendation quantity ratio are set in a parameter form according to flexible changes of compliance management policies to form a product recommendation strategy model.
S4: and (3) recommending strategy selection, selecting and assembling recommended products according to the product data generated in the S1 and the S2 and by combining strategy model parameters set in the S3, and finally calculating and outputting the products meeting various conditions according to the model parameters, wherein a specific strategy selection process is shown in a figure 2, so that the aims of different customers for obtaining different recommended product list data and marketing of thousands of people are finally fulfilled, and marketing benefits are improved.
S5: recommending product assembly, recommending products according to the model selected by the strategy, recommending products by a customer manager/branch bank and a head office, and displaying the products to the customer through a mobile phone bank or an H5 WeChat page to select the products, thereby achieving the purpose of product marketing.
Technical personnel need to firstly realize the customized setting of rule conditions which need to be met by product recommendation from an online interface and simultaneously complete the mapping of the rule conditions into a reasonable product selection model; technical personnel need to consider how to more quickly finish product recommendation so as to reduce response time consumption, and meanwhile, rules need to be abstractly modeled to be made into configurable items, so that flexible rule change can be coped with, the rules can be guaranteed to take effect in real time, and business personnel can quickly strain under the scenes of coping with compliance risks and the like.
The core of the invention is from interface rule setting to marketing rule model generation to real-time product recommendation. The rule setting real-time effect is the characteristic of the invention, and can more flexibly deal with the service change and the policy change.
Fig. 5 is a schematic diagram of a computer device for executing a product recommendation implemented by the present invention, and as shown in fig. 5, an embodiment of the present invention further provides a computer device 500, which includes a memory 510, a processor 520, and a computer program 530 stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements a product recommendation method as described above.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the above-mentioned product recommendation method.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned product recommendation method.
The embodiment of the invention also provides a product recommending device, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to a product recommendation method, the implementation of the device can refer to the implementation of the product recommendation method, and repeated parts are not repeated.
Fig. 6 is a schematic diagram of a product recommendation device according to an embodiment of the present invention, and as shown in fig. 6, a product recommendation device is further provided according to an embodiment of the present invention.
When the product recommendation device provided by the embodiment of the present invention is implemented specifically, in an embodiment, the product recommendation device includes:
the model recommended product list determining module 601 is configured to determine a model recommended product list according to the product sales data and the historical purchase data of the customer;
a manual recommendation data obtaining module 602, configured to obtain input manual recommendation data;
a marketing rule model parameter determining module 603, configured to determine a marketing rule model parameter in a parameter configuration manner;
the product recommendation strategy determination module 604 is configured to determine a product recommendation strategy according to the model recommendation product list, the manual recommendation data, and the marketing rule model parameters;
the personalized recommended product determining module 605 is configured to determine a personalized recommended product according to the product recommendation policy.
When the product recommendation device provided in an embodiment of the present invention is implemented specifically, in an embodiment, the model recommendation product list determining module is specifically configured to:
acquiring product sales data and customer historical purchase data from a trading system in real time through Kafka;
and classifying the product sales data by using MapReduce, sequencing each product type according to the product sales, performing weight adjustment on the products by combining the historical purchase data of the customers, and determining a model recommended product list.
In specific implementation of the product recommendation apparatus provided in an embodiment of the present invention, in an embodiment, the manual recommendation data includes: recommending data by lines, recommending data of maintaining customer products by a customer manager and recommending data of recommending key products by a head office.
In an embodiment of the invention, when the product recommendation device provided in the embodiment of the present invention is implemented specifically, the marketing rule model parameter determination module is specifically configured to:
determining parameter configuration data in response to selection of a parameter configuration item by a customer manager; the parameter configuration item comprises: setting the professional qualification, setting the three-level sales qualification of a client manager, and comparing the product recommendation requirement based on the client risk level, the requirement of qualified investors, the model and the accurate recommendation quantity;
and determining parameters of the marketing rule model according to the parameter configuration data.
When the product recommendation apparatus provided in an embodiment of the present invention is implemented specifically, in an embodiment, the product recommendation policy determining module is specifically configured to:
acquiring an uploading mobile phone number and a customer manager number from the marketing rule model parameters;
judging whether the client is the client of the current bank or not according to the mobile phone number and the client manager number, if so, judging whether the client manager exists or not, and if so, acquiring the client risk level and the manager qualification from the marketing rule model parameters;
judging whether the sales qualification of the customer manager exists or not according to the risk level of the customer and the qualification of the manager, and reading a model recommended product list and manual recommended data if the sales qualification of the customer manager exists; when the manual recommendation data is empty, selecting the customer manager number to obtain the corresponding uplink service qualification; determining that the manual recommendation content is written in the manual recommendation data according to the uplink physical qualification and the client risk level;
and (4) according to the model recommended product list and the manual recommended data, combining the qualification of a manager and the risk level of a client, and determining a product recommendation strategy according to a quantity rule.
When the product recommendation device provided by the embodiment of the present invention is implemented specifically, in an embodiment, the personalized recommended product determination module is specifically configured to:
and selecting and assembling the recommended products according to the product recommendation strategy, and determining the personalized recommended products.
To sum up, an embodiment of the present invention provides a product recommendation method and apparatus, where the method includes: determining a model recommended product list according to the product sales data and the historical purchase data of the customer; acquiring input manual recommendation data; determining parameters of a marketing rule model by adopting a parameter configuration mode; determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters; and determining the personalized recommended product according to the product recommendation strategy. Different products can be recommended for the client based on a big data algorithm and a recommendation strategy model, the purpose that the client recommends thousands of people and sales is achieved accurately, the client is stimulated to purchase various products of a bank, and the bank performance is improved. The system is relatively perfect, a recommendation rule setting interface is provided, and a recommendation model is automatically generated for real-time product recommendation. The method has good flexibility, and business personnel can flexibly set rules according to activity conditions through parameter control. The maintenance cost is low: related information can be set through parameters, only parameters need to be adjusted if the system is required to be changed in the maintenance process, and version development is generally not required. The method has the characteristics of high response and high complexity rule support, and can bring better use experience to customers.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations, and various types of data such as personal identity data, operation data, behavior data and the like related to individuals, clients, crowds and the like are authorized.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (15)
1. A method for recommending products, comprising:
determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
acquiring input manual recommendation data;
determining parameters of a marketing rule model by adopting a parameter configuration mode;
determining a product recommendation strategy according to the model recommended product list, the manual recommendation data and the marketing rule model parameters;
and determining the personalized recommended product according to the product recommendation strategy.
2. The method of claim 1, wherein determining a model recommended product list based on the product sales data and the customer historical purchase data comprises:
acquiring product sales data and customer historical purchase data from a transaction system in real time through Kafka;
and classifying the product sales data by using MapReduce, sequencing each product type according to the product sales, performing weight adjustment on the products by combining the historical purchase data of the customers, and determining a model recommended product list.
3. The method of claim 1, wherein the manually recommending data comprises: recommending data by lines, recommending data of maintenance customer products by a customer manager, and recommending data of key product recommendation by a head office.
4. The method of claim 1, wherein determining marketing rule model parameters using the parameter configuration comprises:
determining parameter configuration data in response to selection of a parameter configuration item by a customer manager; the parameter configuration item comprises: setting the professional qualification, setting the three-level sales qualification of a client manager, and comparing the product recommendation requirement based on the client risk level, the requirement of qualified investors, the model and the accurate recommendation quantity;
and determining parameters of the marketing rule model according to the parameter configuration data.
5. The method of claim 1, wherein determining the product recommendation strategy based on the model recommended product list, the manual recommendation data, and the marketing rules model parameters comprises:
acquiring an uploading mobile phone number and a customer manager number from the marketing rule model parameters;
judging whether the client is the client in the local bank or not according to the mobile phone number and the client manager number, if so, judging whether the client manager exists or not, and if so, acquiring the client risk level and the manager qualification from the marketing rule model parameters;
judging whether the sales qualification of the customer manager exists or not according to the risk level of the customer and the qualification of the manager, and reading a model recommended product list and manual recommended data if the sales qualification of the customer manager exists; when the manual recommendation data is empty, selecting the customer manager number to obtain the corresponding uploading and sending management qualification; determining that the manual recommendation content is written in the manual recommendation data according to the uplink physical qualification and the client risk level;
and determining a product recommendation strategy according to the model recommendation product list and the manual recommendation data, the manager qualification and the client risk level and the quantity rule.
6. The method of claim 1, wherein determining a personalized recommended product according to a product recommendation policy comprises:
and selecting and assembling the recommended products according to the product recommendation strategy, and determining the personalized recommended products.
7. A product recommendation device, comprising:
the model recommended product list determining module is used for determining a model recommended product list according to the product sales data and the historical purchase data of the customer;
the manual recommendation data acquisition module is used for acquiring input manual recommendation data;
the marketing rule model parameter determining module is used for determining marketing rule model parameters in a parameter configuration mode;
the product recommendation strategy determination module is used for determining a product recommendation strategy according to the model recommendation product list, the artificial recommendation data and the marketing rule model parameters;
and the personalized recommended product determining module is used for determining a personalized recommended product according to the product recommending strategy.
8. The apparatus of claim 7, wherein the model recommended products list determination module is specifically configured to:
acquiring product sales data and customer historical purchase data from a trading system in real time through Kafka;
and classifying the product sales data by using MapReduce, sequencing each product type according to the product sales, performing weight adjustment on the products by combining the historical purchase data of the customers, and determining a model recommended product list.
9. The apparatus of claim 7, wherein the manual recommendation data comprises: recommending data by lines, recommending data of maintenance customer products by a customer manager, and recommending data of key product recommendation by a head office.
10. The apparatus of claim 7, wherein the marketing rules model parameters determination module is specifically configured to:
responding to the selection of the parameter configuration items by the client manager, and determining parameter configuration data; the parameter configuration item comprises: setting the working qualification, setting the third-level sales qualification of a client manager, and comparing the product recommendation requirement based on the risk level of the client, the requirement of qualified investors, a model and the accurate recommendation quantity;
and determining parameters of the marketing rule model according to the parameter configuration data.
11. The apparatus of claim 7, wherein the product recommendation policy determination module is specifically configured to:
acquiring an uploading mobile phone number and a customer manager number from the marketing rule model parameters;
judging whether the client is the client in the local bank or not according to the mobile phone number and the client manager number, if so, judging whether the client manager exists or not, and if so, acquiring the client risk level and the manager qualification from the marketing rule model parameters;
judging whether the sales qualification of the customer manager exists or not according to the risk level of the customer and the qualification of the manager, and reading a model recommended product list and manual recommended data if the sales qualification of the customer manager exists; when the manual recommendation data is empty, selecting the customer manager number to obtain the corresponding uploading and sending management qualification; determining that the manual recommendation content is written in the manual recommendation data according to the uplink physical qualification and the client risk level;
and determining a product recommendation strategy according to the model recommendation product list and the manual recommendation data, the manager qualification and the client risk level and the quantity rule.
12. The apparatus of claim 7, wherein the personalized recommended products determination module is specifically configured to:
and selecting and assembling the recommended products according to the product recommendation strategy, and determining the personalized recommended products.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 6 when executing the computer program.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.
15. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508301.6A CN115731003A (en) | 2022-11-28 | 2022-11-28 | Product recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211508301.6A CN115731003A (en) | 2022-11-28 | 2022-11-28 | Product recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115731003A true CN115731003A (en) | 2023-03-03 |
Family
ID=85299225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211508301.6A Pending CN115731003A (en) | 2022-11-28 | 2022-11-28 | Product recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115731003A (en) |
-
2022
- 2022-11-28 CN CN202211508301.6A patent/CN115731003A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11694270B2 (en) | Objective achievement portfolio generating device, program, and method | |
| US8122429B2 (en) | Method, system and program product for developing a data model in a data mining system | |
| US11694267B2 (en) | Automation and latency remediation for secure messaging systems | |
| CN109035028B (en) | Intelligent consultation strategy generation method and device, electronic equipment and storage medium | |
| AU2013221926A1 (en) | Methods and systems for consumer lending | |
| US8775296B2 (en) | Social based automatic trading of currencies, commodities, securities and other financial instruments | |
| US12002096B1 (en) | Artificial intelligence supported valuation platform | |
| NO20230189A1 (en) | Environmental, social, and governance (esg) performance trends | |
| US20210232970A1 (en) | Systems and methods for risk-sensitive reinforcement learning | |
| Becker | Non-wage job characteristics and the case of the missing margin | |
| US20150278957A1 (en) | Method of Determining Sufficient Financial Resources for Retirement | |
| CN115731003A (en) | Product recommendation method and device | |
| CN113590692A (en) | Three-stage crowd mining condition optimization method and system | |
| CN113240513A (en) | Method for determining user credit line and related device | |
| CN113393320A (en) | Enterprise financial service risk prediction method and device | |
| Van de Ven | LINDA: A dynamic microsimulation model for analysing policy effects on the evolving population cross-section | |
| US20240119529A1 (en) | Machine learning based personalized ethical interest and sensitivity profile generation for investment management | |
| US20230267542A1 (en) | System and method for analysing financial products | |
| WO2022024381A1 (en) | Information processing device, information processing method, and recording medium | |
| US11803915B1 (en) | Computing system for adaptive investment recommendations | |
| US20230062714A1 (en) | System and method for generating and updating a user profile for an institution based on peer group data | |
| WO2022024382A1 (en) | Display control device, display control method, and recording medium | |
| Goel | PROJECT SEMESTER REPORT | |
| CN117522510A (en) | Product recommendation method and device | |
| CN117745443A (en) | Asset expected benefit estimation method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |